For single-view clothed human reconstruction, the fashionable PIFu-like framework depends on the pixel-aligned feature essentially, while this leads to depth ambiguity and inaccuracy of representation. Additionally, this task faces the inherent problem of the lack of invisible information. To solve these two problems, we propose depth-guided pixel-aligned feature and multi-view consistency prior to constrain representation learning of the single-view reconstruction task. The difference, between the depth values of points and estimated depth map, is used to filter pixel-aligned features. Thus, the image encoder can focus on capturing the feature of the visible part which is more effective in feature representation. The method introduces contrastive learning and masked autoencoder to achieve consistency of SMPL vertex features in each view which helps model to imagine invisible information. The experimental results show that the proposed method enables the feature to represent surface details more efficiently, thus achieves more reasonable and accurate representation learning. The qualitative and quantitative evaluations on the public and commercial datasets show that the proposed method can achieve better performance than previous implicit representation based methods.

Accurate segmentation of 3D point clouds in indoor scenes remains a challenging task, often hindered by the labor-intensive nature of data annotation. While weakly supervised learning approaches have shown promise in leveraging partial annotations, they frequently struggle with imbalanced performance between foreground and background elements due to the complex structures and proximity of objects in indoor environments. To address this issue, we propose a novel foreground-aware label enhancement method utilizing visual boundary priors. Our approach projects 3D point clouds onto 2D planes and applies 2D image segmentation to generate pseudo-labels for foreground objects. These labels are subsequently back-projected into 3D space and used to train an initial segmentation model. We further refine this process by incorporating prior knowledge from projected images to filter the predicted labels, followed by model retraining. We introduce this technique as the Foreground Boundary Prior (FBP), a versatile, plug-and-play module designed to enhance various weakly supervised point cloud segmentation methods. We demonstrate the efficacy of our approach on the widely-used 2D-3D-Semantic dataset, employing both random-sample and bounding-box based weak labeling strategies. Our experimental results show significant improvements in segmentation performance across different architectural backbones, highlighting the method's effectiveness and portability.

Abstract Clothed human re‐construction from a monocular image is challenging due to occlusion, depth‐ambiguity and variations of body poses. Recently, shape representation based on an implicit function, compared to explicit representation such as mesh and voxel, is more capable with complex topology of clothed human. This is mainly achieved by using pixel‐aligned features, facilitating implicit function to capture local details. But such methods utilize an identical feature map for all sampled points to get local features, making their models occlusion‐agnostic in the encoding stage. The decoder, as implicit function, only maps features and does not take occlusion into account explicitly. Thus, these methods fail to generalize well in poses with severe self‐occlusion. To address this, we present OaIF to encode local features conditioned in visibility of SMPL vertices. OaIF projects SMPL vertices onto image plane to obtain image features masked by visibility. Vertices features integrated with geometry information of mesh are then feed into a GAT network to encode jointly. We query hybrid features and occlusion factors for points through cross attention and learn occupancy fields for clothed human. The experiments demonstrate that OaIF achieves more robust and accurate re‐construction than the state of the art on both public datasets and wild images.